Intelligent adjustment method and device for product ratio and computer equipment

Abstract

The invention relates to an intelligent adjustment method and device for a product ratio and computer equipment. The method comprises the following steps: obtaining product sales information and product feedback information of each product type of each store, and for each store, identifying preference product information of each preference product type of the store based on the product sales information of each product type of the store; identifying product evaluation information of each product type through a product data model based on the product feedback information of each product type, and generating product proportion adjustment information of each product type based on the product evaluation information of each product type and preference product information of each preference product type; and collecting new product feedback information of each product type, and readjusting the product proportion adjustment information of each product type based on the new product feedback information of each product type to obtain target product proportion information of each product type. By adopting the method, the product meal delivery efficiency and meal delivery accuracy of the intelligent liquid delivery machine can be improved.

Description

Technical Field

[0001] The present application relates to the fields of big data analysis and automation equipment technology, and in particular to a method, device and computer equipment for intelligently adjusting product ratios. Background Art

[0002] With the continuous advancement of science and technology in the fields of big data analysis, intelligent manufacturing, and product formulation optimization, more and more companies are beginning to use big data analysis to optimize product ratios and improve production efficiency and quality. Intelligent manufacturing technology uses automated equipment and intelligent control systems to achieve full monitoring and intelligent decision-making during the production process, thereby improving production efficiency and product quality. Product formulation optimization technology uses scientific methods and modern technologies to optimize product formulas to enhance product performance and quality.

[0003] With existing technologies, companies typically collect and analyze sales data to understand product sales in different regions and adjust product mixes accordingly. However, manual data collection and mix adjustment is time-consuming and inaccurate, and the accuracy of product mix adjustments is also low. Furthermore, the accuracy of product mix adjustments varies widely across regions and stores, resulting in low product mix accuracy. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for intelligent adjustment of product ratios to address the above technical problems.

[0005] In a first aspect, the present application provides a method for intelligently adjusting product ratios, comprising:

[0006] Acquire product sales information of each product type at each store and product feedback information of each product type at each store, and identify, for each store, preferred product information of each preferred product type at the store based on the product sales information of each product type at the store;

[0007] Based on the product feedback information of each of the product types, identifying the product evaluation information of each of the product types through a product data model, and generating product ratio adjustment information for each of the product types based on the product evaluation information of each of the product types and the preferred product information of each of the preferred product types;

[0008] New product feedback information of each of the product types is collected, and based on the new product feedback information of each of the product types, the product ratio adjustment information of each of the product types is readjusted to obtain the target product ratio information of each of the product types.

[0009] Optionally, identifying the preferred product information of each preferred product type of the store based on the product sales information of each product type of the store includes:

[0010] For each product type, split the product sales information of the product type into sales data of each sales product, and construct a sales distribution curve for each sales product based on the sales data of each sales product;

[0011] identifying sales preference information of each of the sales products based on a sales distribution curve of each of the sales products, and screening target preferred sales products from among the sales products based on the sales preference information of each of the sales products;

[0012] The product type in which the preferred sales product exists is regarded as the preferred product type, and each preferred sales product of each preferred product is regarded as the preferred product information of each preferred product type.

[0013] Optionally, identifying product evaluation information of each product type based on the product feedback information of each product type through a product data model includes:

[0014] For each product type, the product feedback information of the product type is divided into feedback content of each feedback type, and the feedback evaluation content of each feedback type is identified according to the feedback evaluation strategy of each feedback type;

[0015] The feedback evaluation content of each feedback type is used as the product evaluation information of the product type.

[0016] Optionally, generating product ratio adjustment information for each product type based on the product evaluation information of each product type and the preferred product information of each preferred product type includes:

[0017] Based on the preferred sales products of each preferred product type and the feedback evaluation content of each feedback type of each preferred product type, identifying first preferred product ratio information of each preferred sales product of each preferred product type through a first preferred product analysis network;

[0018] Based on each non-preferred sales product of each preferred product type, each sales product of each non-preferred product type, and the feedback evaluation content of each feedback type of each product type, identifying, by a second preferred product analysis network, second preferred product ratio information of each non-preferred sales product of each preferred product type and third preferred product ratio information of each sales product of each non-preferred product type;

[0019] Based on the first preference product ratio information of each preferred sales product of each preferred product type, the second preference product ratio information of each non-preferred sales product of each preference product type, and the third preference product ratio information of each sales product of each non-preferred product type, product ratio adjustment information of each product type is generated.

[0020] Optionally, before readjusting the product ratio adjustment information of each product type based on the new product feedback information of each product type to obtain the target product ratio information of each product type, the method further includes:

[0021] Based on the new product feedback information of each product type, query the sub-product feedback content of each sales product of each product type, and for each product type, based on the sub-product feedback content of each sales product of the product type, extract the product ratio feedback content of each sales product through the semantic extraction network;

[0022] For each sold product, based on the product proportion feedback content of the sold product, sub-proportion feedback data of each ingredient type of the sold product is identified.

[0023] Optionally, the product ratio adjustment information of each product type is readjusted based on the new product feedback information of each product type to obtain the target product ratio information of each product type, including:

[0024] For each sales product, based on the sub-ratio feedback data of each ingredient type of the sales product, identify the ratio feedback requirements of each ingredient type of each sales product, and generate new product ratio adjustment information for each sales product through the ratio optimization network based on the ratio feedback requirements of each ingredient type of each sales product;

[0025] Based on the new product mix adjustment information of each sales product and the product mix adjustment information of each sales product, target product mix information of each product type is generated.

[0026] In a second aspect, the present application further provides an intelligent adjustment device for product ratio, comprising:

[0027] an acquisition module, configured to acquire product sales information of each product type of each store and product feedback information of each product type of each store, and identify, for each store, preferred product information of each preferred product type of the store based on the product sales information of each product type of the store;

[0028] a generating module, configured to identify, based on the product feedback information of each product type and using a product data model, product evaluation information of each product type, and generate product ratio adjustment information for each product type based on the product evaluation information of each product type and the preferred product information of each preferred product type;

[0029] The adjustment module is used to collect new product feedback information of each product type, and based on the new product feedback information of each product type, readjust the product ratio adjustment information of each product type to obtain the target product ratio information of each product type.

[0030] Optionally, the acquisition module is specifically configured to:

[0031] For each product type, split the product sales information of the product type into sales data of each sales product, and construct a sales distribution curve for each sales product based on the sales data of each sales product;

[0032] identifying sales preference information of each of the sales products based on a sales distribution curve of each of the sales products, and screening target preferred sales products from among the sales products based on the sales preference information of each of the sales products;

[0033] The product type in which the preferred sales product exists is regarded as the preferred product type, and each preferred sales product of each preferred product is regarded as the preferred product information of each preferred product type.

[0034] Optionally, the generating module is specifically configured to:

[0035] For each product type, the product feedback information of the product type is divided into feedback content of each feedback type, and the feedback evaluation content of each feedback type is identified according to the feedback evaluation strategy of each feedback type;

[0036] The feedback evaluation content of each feedback type is used as the product evaluation information of the product type.

[0037] Optionally, the generating module is specifically configured to:

[0038] Based on the preferred sales products of each preferred product type and the feedback evaluation content of each feedback type of each preferred product type, identifying first preferred product ratio information of each preferred sales product of each preferred product type through a first preferred product analysis network;

[0039] Based on each non-preferred sales product of each preferred product type, each sales product of each non-preferred product type, and the feedback evaluation content of each feedback type of each product type, identifying, by a second preferred product analysis network, second preferred product ratio information of each non-preferred sales product of each preferred product type and third preferred product ratio information of each sales product of each non-preferred product type;

[0040] Based on the first preference product ratio information of each preferred sales product of each preferred product type, the second preference product ratio information of each non-preferred sales product of each preference product type, and the third preference product ratio information of each sales product of each non-preferred product type, product ratio adjustment information of each product type is generated.

[0041] Optionally, the device further includes:

[0042] an extraction module configured to query sub-product feedback content of each sales product of each product type based on the new product feedback information of each product type, and extract product ratio feedback content of each sales product of each product type based on the sub-product feedback content of each sales product of the product type through a semantic extraction network;

[0043] The identification module is used to identify, for each sales product, sub-proportion feedback data of each ingredient type of the sales product based on the product proportion feedback content of the sales product.

[0044] Optionally, the adjustment module is specifically configured to:

[0045] For each sales product, based on the sub-ratio feedback data of each ingredient type of the sales product, identify the ratio feedback requirements of each ingredient type of each sales product, and generate new product ratio adjustment information for each sales product through the ratio optimization network based on the ratio feedback requirements of each ingredient type of each sales product;

[0046] Based on the new product mix adjustment information of each sales product and the product mix adjustment information of each sales product, target product mix information of each product type is generated.

[0047] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0049] In a fifth aspect, the present application provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0050] The above-mentioned intelligent adjustment method, device and computer equipment for product ratios obtains product sales information of each product type in each store and product feedback information of each product type in each store, and for each store, identifies the preferred product information of each preferred product type in the store based on the product sales information of each product type in the store; identifies the product evaluation information of each product type through a product data model based on the product feedback information of each product type, and generates product ratio adjustment information for each product type based on the product evaluation information of each product type and the preferred product information of each preferred product type; collects new product feedback information of each product type, and readjusts the product ratio adjustment information of each product type based on the new product feedback information of each product type to obtain the target product ratio information of each product type. This solution conducts a comprehensive analysis by combining the product sales information and product feedback information of each product type in different stores, thereby identifying the preferred product information of the user's preferred product type and the product evaluation information of each product type, and thus comprehensively analyzing the product ratio adjustment information of each product type. Compared to manual adjustments, this solution better adapts to each store's actual customer needs and can efficiently and adaptively adjust the comprehensive ratios of different product types, improving both efficiency and accuracy. This solution also adjusts product ratios based on new product feedback from each product type, intelligently configuring each product type's ratio information bar to best meet user needs, thereby comprehensively improving the accuracy of product ratio adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 Schematic diagram of a flow chart of a method for intelligently adjusting product ratios in one embodiment;

[0053] Figure 2 A schematic diagram of a process flow of an example of intelligent adjustment of product ratios in one embodiment;

[0054] Figure 3This is a structural block diagram of an intelligent device for adjusting product ratios in one embodiment;

[0055] Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0057] The intelligent adjustment method of product ratio provided in the embodiment of the present application can be applied to the intelligent control system for intelligent adjustment of product ratio constructed. The system can be applied to a terminal, which can be but not limited to various personal computers, laptops, mid-range computers, etc. Among them, the terminal conducts a comprehensive analysis by combining the product sales information of each product type in different stores, as well as the product feedback information, so as to identify the user's preferred product information of the preferred product type, as well as the product evaluation information of each product type, and thus comprehensively analyze the product ratio adjustment information of each product type. Compared with manual adjustment, the adjustment of this solution is more suitable for the actual customer needs of each store, and can efficiently perform comprehensive adaptive adjustment of the ratio of different product types, thereby improving the adjustment efficiency and adjustment accuracy. Then this solution can also combine the new product feedback information of each product type, and then adjust the product ratio, so as to intelligently configure the product ratio information bar of each product type to a state that is more suitable for user needs, thereby comprehensively improving the accuracy of product ratio adjustment.

[0058] In an exemplary embodiment, Figure 1 As shown, a method for intelligently adjusting product ratio is provided, which is described by taking the method applied to a terminal as an example, and includes the following steps S101 to S103.

[0059] Step S101, obtain product sales information of each product type of each store and product feedback information of each product type of each store, and for each store, identify the preferred product information of each preferred product type of the store based on the product sales information of each product type of the store.

[0060] In this embodiment, the terminal, in response to the information upload operation of the intelligent liquid dispenser, obtains sales information for each product sold within each product type, thereby obtaining product sales information for each product type. Furthermore, in response to the information upload operation of the staff member, it obtains product feedback information for each product type. The product feedback information for each product type includes feedback content for each product sold within each product type, which may include taste feedback, flavor feedback, material feedback, and quality feedback. The sales information for each product sold includes sales information such as sales volume and sales time for each product sold. Each product sold is a different variety of product sold within each product type, such as, for example, high mountain black tea, tribute tea, and Dahongpao varieties within the black tea product type.

[0061] Next, the terminal identifies the preferred product information for each store's preferred product type based on the store's sales information for each product type. Each preferred product type includes a product type for which a user has a preferred product, and each piece of preferred product information includes the product preferred by each user. The specific identification process will be described in detail later.

[0062] Step S102: Based on the product feedback information of each product type, the product evaluation information of each product type is identified through the product data model, and based on the product evaluation information of each product type and the preferred product information of each preferred product type, the product ratio adjustment information of each product type is generated.

[0063] In this embodiment, the terminal identifies product evaluation information for each product type using a product data model based on product feedback information for each product type. Based on the product evaluation information for each product type and the preferred product information for each preferred product type, the terminal generates product ratio adjustment information for each product type. The product data model corresponds to an artificial intelligence neural network model used for product data analysis and product information evaluation. The specific identification process will be described in detail later. The product ratio adjustment information for each product type is the ingredient quantity adjustment information for each product ingredient list for each product sold that applies to that product type.

[0064] Step S103 , collecting new product feedback information of each product type, and based on the new product feedback information of each product type, readjusting the product ratio adjustment information of each product type to obtain target product ratio information of each product type.

[0065] In this embodiment, the terminal collects new product feedback information for each product type and, based on the new product feedback information for each product type, readjusts the product ratio adjustment information for each product type to obtain target product ratio information for each product type. The target product ratio information is the adjusted target ingredient amounts for each product ingredient list for each product being sold.

[0066] Based on the above solution, by combining the product sales information of each product type in different stores, as well as the product feedback information, a comprehensive analysis is conducted to identify the user's preferred product information of the preferred product type, as well as the product evaluation information of each product type, thereby comprehensively analyzing the product ratio adjustment information of each product type. Compared with manual adjustments, the adjustments of this solution are more suitable for the actual customer needs of each store, and can efficiently and adaptively adjust the comprehensive ratios of different product types, thereby improving the adjustment efficiency and accuracy. Then, this solution can also adjust the product ratio based on the new product feedback information of each product type, thereby intelligently configuring the product ratio information bar of each product type to a state that is more suitable for user needs, thereby comprehensively improving the accuracy of product ratio adjustments.

[0067] Optionally, based on the product sales information of each product type in the store, the preferred product information of each preferred product type in the store is identified, including: for each product type, splitting the product sales information of the product type into sales data of each sales product, and constructing a sales distribution curve for each sales product based on the sales data of each sales product; based on the sales distribution curve of each sales product, identifying the sales bias information of each sales product, and based on the sales bias information of each sales product, screening target preferred sales products among each sales product; taking the product type for which there is a preferred sales product as the preferred product type, and taking each preferred sales product of each preferred product as the preferred product information of each preferred product type.

[0068] In this embodiment, for each product type, the terminal divides the product sales information of the product type into sales data for each product sold, and constructs a sales distribution curve for each product sold based on the sales data for each product sold. The sales distribution curve for each product sold is a sales volume curve chart in a sales distribution table constructed with sales time as the horizontal axis and sales volume as the vertical axis.

[0069] Then, the terminal identifies the sales bias information of each product based on the sales distribution curve of each product. Specifically, based on the sales distribution curve of each product, the terminal extracts the product sales feature information of each product through a linear feature extraction network, and queries the product database for the product sales feature information of each product, identifies the sales bias type of each product, and uses the sales bias type of each product as the sales bias information of each product. Among them, the linear feature extraction network is a linear feature extraction neural network based on linear regression technology. The sales feature information of each product, for example, large sales volume on holidays, a downward sales trend, an upward sales trend, a low level of flat sales trend, a medium level of flat sales trend, a high level of flat sales, a large sales fluctuation curve, etc. For example, each sales bias type has a sales bias type corresponding to large sales on holidays, which is the leisure beverage type; a sales bias type corresponding to a declining sales trend is a decreasing product popularity type; a sales bias type corresponding to an increasing sales trend is an increasing product popularity type; a sales bias type corresponding to a flat and low sales trend is a low product popularity type; a sales bias type corresponding to a medium and low sales trend is a medium product popularity type; a sales bias type corresponding to a flat and high sales trend is a high product popularity type; and a sales bias type corresponding to a large sales fluctuation curve is a targeted product popularity type.

[0070] The terminal selects target preferred sales products from among the sales products based on the sales preference information of the sales products, wherein the target preferred sales products are sales products whose sales preference types belong to the sales preference types preset in the terminal.

[0071] The terminal stores the product type of the preferred sales product as the preferred product type, and stores each preferred sales product of each preferred product as the preferred product information of each preferred product type.

[0072] Based on the above solution, the sales tendency of each product is analyzed by combining the sales time and sales volume of each product, thereby improving the accuracy and comprehensiveness of the product sales tendency analysis.

[0073] Optionally, based on the product feedback information of each product type, the product evaluation information of each product type is identified through the product data model, including: for each product type, splitting the product feedback information of the product type into feedback content of each feedback type, and identifying the feedback evaluation content of each feedback type through the feedback evaluation strategy of each feedback type; and using the feedback evaluation content of each feedback type as the product evaluation information of the product type.

[0074] In this embodiment, for each product type, the terminal divides the product feedback information of the product type into feedback content for each feedback type and identifies the feedback evaluation content for each feedback type using the feedback evaluation strategy for each feedback type. The feedback types include, but are not limited to, taste feedback, service feedback, mouthfeel feedback, quality feedback, and flavor feedback. The terminal presets feedback evaluation strategies for different feedback types, each of which includes the evaluation semantic content range corresponding to the indicator values of each feedback evaluation indicator for each feedback type. Based on each product feedback information, the terminal identifies the feedback semantic content for each feedback type using a semantic recognition network. Then, based on the feedback semantic content for each feedback type, the terminal identifies the feedback evaluation indicator values corresponding to each feedback type using the evaluation semantic content range corresponding to the indicator values of each feedback evaluation indicator for each feedback type, and uses the feedback evaluation indicator values for each feedback type as the feedback content for each feedback type. For example, the indicator values for each feedback type include, for taste feedback, the sourness evaluation indicator, sweetness evaluation indicator, bitterness evaluation indicator, saltiness evaluation indicator, spiciness evaluation indicator, and astringency evaluation indicator.

[0075] Finally, the terminal uses the feedback evaluation content of each feedback type as product evaluation information of the product type.

[0076] Based on the above solution, by respectively identifying the indicator values of each feedback evaluation indicator of each feedback type, the accuracy and comprehensiveness of the feedback evaluation analysis of each feedback type are improved.

[0077] Optionally, based on the product evaluation information of each product type and the preferred product information of each preferred product type, product ratio adjustment information for each product type is generated, including: based on each preferred sales product of each preferred product type and the feedback evaluation content of each feedback type of each preferred product type, identifying the first preference product ratio information of each preferred sales product of each preferred product type through a first preference product analysis network; based on each non-preferred sales product of each preferred product type, each sales product of each non-preferred product type, and the feedback evaluation content of each feedback type of each product type, identifying the second preference product ratio information of each non-preferred sales product of each preferred product type and the third preference product ratio information of each sales product of each non-preferred product type through a second preference product analysis network; based on the first preference product ratio information of each preferred sales product of each preferred product type, the second preference product ratio information of each non-preferred sales product of each preference product type, and the third preference product ratio information of each sales product of each non-preferred product type, product ratio adjustment information for each product type is generated.

[0078] In this embodiment, the terminal uses a first preference product analysis network to identify first preference product ratio information for each preferred sales product within each preferred product type, based on the feedback evaluation content for each preferred sales product within each preferred product type and each feedback type within each preferred product type. The first preference product analysis network and the second preference product analysis network described below are deep learning-based convolutional neural networks trained using sample feedback evaluation content for each feedback type within each preferred sales product type.

[0079] Based on the non-preferred sales products of each preferred product type, the sales products of each non-preferred product type, and the feedback evaluation content of each feedback type of each product type, the terminal uses a second preferred product analysis network to identify second preferred product ratio information for each non-preferred sales product of each preferred product type and third preferred product ratio information for each sales product of each non-preferred product type. Each preferred product ratio information includes a product ratio range for each ingredient type of each sales product.

[0080] For each product sold, the terminal selects the target product ratio of each ingredient type of each product sold based on the actual product ratio of each ingredient type of the product sold and the product ratio range of each ingredient type of the product sold, and uses the deviation between each target product ratio and the reagent product ratio as the sub-ratio adjustment range of each ingredient type of each product sold, and uses the sub-ratio adjustment range of each ingredient type of all products sold of the product type as the product ratio adjustment information of the product sold. Wherein, if the actual product ratio is within the product ratio range, the target product ratio is the actual product ratio, and if the actual product ratio is not within the product ratio range, the target product ratio is the product ratio range boundary value with the smallest deviation from the actual product ratio.

[0081] Based on the above solution, after identifying the product ratio information, the target ratio of each ingredient type of each sales product is screened, thereby improving the ratio accuracy of the target ratio.

[0082] Optionally, based on the new product feedback information of each product type, the product ratio adjustment information of each product type is readjusted to obtain the target product ratio information of each product type, which also includes: based on the new product feedback information of each product type, querying the sub-product feedback content of each sales product of each product type, and for each product type, based on the sub-product feedback content of each sales product of the product type, extracting the product ratio feedback content of each sales product through the semantic extraction network; for each sales product, based on the product ratio feedback content of the sales product, identifying the sub-ratio feedback data of each ingredient type of the sales product.

[0083] In this embodiment, based on the new product feedback information for each product type, the terminal queries the sub-product feedback content for each product sold within each product type. Furthermore, for each product type, based on the sub-product feedback content for each product sold within that product type, the terminal uses a semantic extraction network to extract product ratio feedback content for each product sold. This semantic extraction step directly extracts semantic content related to the ratio. This eliminates the need to separate feedback types and instead directly filters the ratio for each ingredient type, improving the efficiency and accuracy of identifying ratio feedback for each ingredient type.

[0084] For each sold product, based on the product proportion feedback content of the sold product, sub-proportion feedback data of each ingredient type of the sold product is identified, wherein the sub-proportion feedback data of each ingredient type includes the ingredient amount adjustment range of each ingredient type.

[0085] Based on the above solution, after semantic extraction of the product ratio range content of each product type, it is split into sub-ratio feedback data of each ingredient type of each sales product, thereby improving the comprehensiveness and accuracy of the recognition of sub-ratio feedback data of each ingredient type.

[0086] Optionally, based on the new product feedback information of each product type, the product ratio adjustment information of each product type is readjusted to obtain the target product ratio information of each product type, including: for each sales product, based on the sub-ratio feedback data of each ingredient type of the sales product, identifying the ratio feedback requirements of each ingredient type of each sales product, and based on the ratio feedback requirements of each ingredient type of each sales product, generating new product ratio adjustment information for each sales product through a ratio optimization network; based on the new product ratio adjustment information of each sales product and the product ratio adjustment information of each sales product, generating the target product ratio information of each product type.

[0087] In this embodiment, the terminal identifies the required proportion feedback for each ingredient type for each product sold based on the sub-proportion feedback data for each ingredient type. This proportion feedback requirement specifies the required proportion range for each ingredient type for each product sold. Because users can only provide approximate ranges when providing feedback, such as "too sour," "a little sour," "a bit sour," "very sour," or "just the right amount of sour," the proportion range for each ingredient type is determined based on the semantic content of each user's feedback.

[0088] Based on the feedback on the ratio of each ingredient type for each product sold, the terminal generates new product ratio adjustment information for each product sold through a ratio optimization network. This new product ratio adjustment information includes the new ratio adjustment amount for each ingredient type of the product sold. This ratio optimization network is a classifier neural network based on the attention mechanism.

[0089] The terminal then generates target product ratio information for each product type based on the new product ratio adjustment information and the product ratio adjustment information for each product type. This target product ratio information is the sum of the new ratio adjustment amounts for each ingredient type in the new product ratio adjustment information and the ratio adjustment amounts for each ingredient type in the product ratio adjustment information.

[0090] Based on the above solution, the target product ratio information of each product type is generated by adjusting the ingredients of the feedback data, thereby improving the ratio adaptability of the target product ratio information of each product type and the user experience effect.

[0091] The application also provides an example of intelligent adjustment of product ratios, such as Figure 2 As shown, the specific processing process includes the following steps:

[0092] Step S201 : obtaining product sales information of each product type in each store and product feedback information of each product type in each store.

[0093] Step S202 : for each product type, split the product sales information of the product type into sales data of each sold product, and construct a sales distribution curve of each sold product based on the sales data of each sold product.

[0094] Step S203 : identifying the sales preference information of each sales product based on the sales distribution curve of each sales product, and screening target preferred sales products from among the sales products based on the sales preference information of each sales product.

[0095] In step S204, the product type of the preferred sales product is used as the preferred product type, and the preferred sales products of each preferred product are used as the preferred product information of each preferred product type.

[0096] Step S205 : for each product type, split the product feedback information of the product type into feedback contents of each feedback type, and identify the feedback evaluation contents of each feedback type through the feedback evaluation strategy of each feedback type.

[0097] Step S206: Using the feedback evaluation content of each feedback type as product evaluation information of the product type.

[0098] Step S207 : Based on the preferred sales products of each preferred product type and the feedback evaluation content of each feedback type of each preferred product type, the first preferred product ratio information of each preferred sales product of each preferred product type is identified through the first preferred product analysis network.

[0099] Step S208, based on the non-preferred sales products of each preferred product type, the sales products of each non-preferred product type, and the feedback evaluation content of each feedback type of each product type, the second preference product ratio information of each non-preferred sales product of each preferred product type and the third preference product ratio information of each sales product of each non-preferred product type are identified through the second preference product analysis network.

[0100] Step S209: Generate product ratio adjustment information for each product type based on the first preference product ratio information of each preferred sales product of each preferred product type, the second preference product ratio information of each non-preferred sales product of each preference product type, and the third preference product ratio information of each sales product of each non-preferred product type.

[0101] Step S210: collecting new product feedback information of each product type.

[0102] Step S211, based on the new product feedback information of each product type, query the sub-product feedback content of each sales product of each product type, and for each product type, based on the sub-product feedback content of each sales product of the product type, extract the product ratio feedback content of each sales product through the semantic extraction network.

[0103] Step S212 : for each sales product, based on the product proportion feedback content of the sales product, identifying the sub-proportion feedback data of each ingredient type of the sales product.

[0104] Step S213: For each sales product, based on the sub-proportion feedback data of each ingredient type of the sales product, identify the proportion feedback requirements of each ingredient type of each sales product, and based on the proportion feedback requirements of each ingredient type of each sales product, generate new product proportion adjustment information for each sales product through the proportion optimization network.

[0105] Step S214 : generating target product ratio information for each product type based on the new product ratio adjustment information for each sales product and the product ratio adjustment information for each sales product.

[0106] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0107] Based on the same inventive concept, embodiments of the present application also provide an intelligent product ratio adjustment device for implementing the aforementioned intelligent product ratio adjustment method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the intelligent product ratio adjustment device provided below can be found in the limitations of the intelligent product ratio adjustment method described above and will not be repeated here.

[0108] In an exemplary embodiment, Figure 3 As shown, a device for intelligently adjusting product ratio is provided, comprising: an acquisition module 310, a generation module 320 and an adjustment module 330, wherein:

[0109] an acquisition module 310 for acquiring product sales information of each product type at each store and product feedback information of each product type at each store, and identifying, for each store, preferred product information of each preferred product type at the store based on the product sales information of each product type at the store;

[0110] a generating module 320 for identifying, based on the product feedback information of each product type and using a product data model, product evaluation information of each product type, and generating product ratio adjustment information for each product type based on the product evaluation information of each product type and the preferred product information of each preferred product type;

[0111] The adjustment module 330 is used to collect new product feedback information of each product type, and based on the new product feedback information of each product type, readjust the product ratio adjustment information of each product type to obtain the target product ratio information of each product type.

[0112] Optionally, the acquisition module 310 is specifically configured to:

[0113] For each product type, split the product sales information of the product type into sales data of each sales product, and construct a sales distribution curve for each sales product based on the sales data of each sales product;

[0114] identifying sales preference information of each of the sales products based on a sales distribution curve of each of the sales products, and screening target preferred sales products from among the sales products based on the sales preference information of each of the sales products;

[0115] The product type in which the preferred sales product exists is regarded as the preferred product type, and each preferred sales product of each preferred product is regarded as the preferred product information of each preferred product type.

[0116] Optionally, the generating module 320 is specifically configured to:

[0117] For each product type, the product feedback information of the product type is divided into feedback content of each feedback type, and the feedback evaluation content of each feedback type is identified according to the feedback evaluation strategy of each feedback type;

[0118] The feedback evaluation content of each feedback type is used as the product evaluation information of the product type.

[0119] Optionally, the generating module 320 is specifically configured to:

[0120] Based on the preferred sales products of each preferred product type and the feedback evaluation content of each feedback type of each preferred product type, identifying first preferred product ratio information of each preferred sales product of each preferred product type through a first preferred product analysis network;

[0121] Based on each non-preferred sales product of each preferred product type, each sales product of each non-preferred product type, and the feedback evaluation content of each feedback type of each product type, identifying, by a second preferred product analysis network, second preferred product ratio information of each non-preferred sales product of each preferred product type and third preferred product ratio information of each sales product of each non-preferred product type;

[0122] Based on the first preference product ratio information of each preferred sales product of each preferred product type, the second preference product ratio information of each non-preferred sales product of each preference product type, and the third preference product ratio information of each sales product of each non-preferred product type, product ratio adjustment information of each product type is generated.

[0123] Optionally, the device further includes:

[0124] an extraction module configured to query sub-product feedback content of each sales product of each product type based on the new product feedback information of each product type, and extract product ratio feedback content of each sales product of each product type based on the sub-product feedback content of each sales product of the product type through a semantic extraction network;

[0125] The identification module is used to identify, for each sales product, sub-proportion feedback data of each ingredient type of the sales product based on the product proportion feedback content of the sales product.

[0126] Optionally, the adjustment module 330 is specifically configured to:

[0127] For each sales product, based on the sub-ratio feedback data of each ingredient type of the sales product, identify the ratio feedback requirements of each ingredient type of each sales product, and generate new product ratio adjustment information for each sales product through the ratio optimization network based on the ratio feedback requirements of each ingredient type of each sales product;

[0128] Based on the new product mix adjustment information of each sales product and the product mix adjustment information of each sales product, target product mix information of each product type is generated.

[0129] Each module in the intelligent product ratio adjustment device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0130] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for intelligently adjusting the product ratio is implemented. The display unit of the computer device is used to form a visually visible image, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0131] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0132] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the method for intelligently adjusting product ratios when executing the computer program.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for intelligently adjusting product ratios are implemented.

[0134] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of a method for intelligently adjusting product ratios.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0136] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0137] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for intelligently adjusting product ratios, characterized in that: The method comprises: Acquire product sales information of each product type at each store and product feedback information of each product type at each store, and identify, for each store, preferred product information of each preferred product type at the store based on the product sales information of each product type at the store; Based on the product feedback information of each of the product types, identifying the product evaluation information of each of the product types through a product data model, and generating product ratio adjustment information for each of the product types based on the product evaluation information of each of the product types and the preferred product information of each of the preferred product types; New product feedback information of each of the product types is collected, and based on the new product feedback information of each of the product types, the product ratio adjustment information of each of the product types is readjusted to obtain the target product ratio information of each of the product types.

2. The method according to claim 1, characterized in that The identifying, based on the product sales information of each product type of the store, the preferred product information of each preferred product type of the store includes: For each product type, split the product sales information of the product type into sales data of each sales product, and construct a sales distribution curve for each sales product based on the sales data of each sales product; identifying sales preference information of each of the sales products based on a sales distribution curve of each of the sales products, and screening target preferred sales products from among the sales products based on the sales preference information of each of the sales products; The product type in which the preferred sales product exists is regarded as the preferred product type, and each preferred sales product of each preferred product is regarded as the preferred product information of each preferred product type.

3. The method according to claim 2, characterized in that The identifying of product evaluation information of each product type based on the product feedback information of each product type through a product data model includes: For each product type, the product feedback information of the product type is divided into feedback content of each feedback type, and the feedback evaluation content of each feedback type is identified according to the feedback evaluation strategy of each feedback type; The feedback evaluation content of each feedback type is used as the product evaluation information of the product type.

4. The method according to claim 3, characterized in that Generating product ratio adjustment information for each product type based on the product evaluation information of each product type and the preferred product information of each preferred product type includes: Based on the preferred sales products of each preferred product type and the feedback evaluation content of each feedback type of each preferred product type, identifying first preferred product ratio information of each preferred sales product of each preferred product type through a first preferred product analysis network; Based on each non-preferred sales product of each preferred product type, each sales product of each non-preferred product type, and the feedback evaluation content of each feedback type of each product type, identifying, by a second preferred product analysis network, second preferred product ratio information of each non-preferred sales product of each preferred product type and third preferred product ratio information of each sales product of each non-preferred product type; Based on the first preference product ratio information of each preferred sales product of each preferred product type, the second preference product ratio information of each non-preferred sales product of each preference product type, and the third preference product ratio information of each sales product of each non-preferred product type, product ratio adjustment information of each product type is generated.

5. The method according to claim 1, wherein Before re-adjusting the product ratio adjustment information of each product type based on the new product feedback information of each product type to obtain the target product ratio information of each product type, the method further includes: Based on the new product feedback information of each product type, query the sub-product feedback content of each sales product of each product type, and for each product type, based on the sub-product feedback content of each sales product of the product type, extract the product ratio feedback content of each sales product through the semantic extraction network; For each sold product, based on the product proportion feedback content of the sold product, sub-proportion feedback data of each ingredient type of the sold product is identified.

6. The method according to claim 5, characterized in that The method of re-adjusting the product ratio adjustment information of each product type based on the new product feedback information of each product type to obtain the target product ratio information of each product type includes: For each sales product, based on the sub-ratio feedback data of each ingredient type of the sales product, identify the ratio feedback requirements of each ingredient type of each sales product, and generate new product ratio adjustment information for each sales product through the ratio optimization network based on the ratio feedback requirements of each ingredient type of each sales product; Based on the new product mix adjustment information of each sales product and the product mix adjustment information of each sales product, target product mix information of each product type is generated.

7. An intelligent device for adjusting product ratio, characterized in that: The device comprises: an acquisition module, configured to acquire product sales information of each product type of each store and product feedback information of each product type of each store, and identify, for each store, preferred product information of each preferred product type of the store based on the product sales information of each product type of the store; a generating module, configured to identify, based on the product feedback information of each product type and using a product data model, product evaluation information of each product type, and generate product ratio adjustment information for each product type based on the product evaluation information of each product type and the preferred product information of each preferred product type; The adjustment module is used to collect new product feedback information of each product type, and based on the new product feedback information of each product type, readjust the product ratio adjustment information of each product type to obtain the target product ratio information of each product type.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images